Paper: Discriminative Learning over Constrained Latent Representations

ACL ID N10-1066
Title Discriminative Learning over Constrained Latent Representations
Venue Human Language Technologies
Session Main Conference
Year 2010

This paper proposes a general learning frame- work for a class of problems that require learn- ing over latent intermediate representations. Many natural language processing (NLP) de- cision problems are defined over an expressive intermediate representation that is not explicit in the input, leaving the algorithm with both the task of recovering a good intermediate rep- resentation and learning to classify correctly. Most current systems separate the learning problem into two stages by solving the first step of recovering the intermediate representa- tion heuristically and using it to learn the final classifier. This paper develops a novel joint learning algorithm for both tasks, that uses the final prediction to guide the selection of the best intermediate representation. We evalu- ate o...